[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-81513-en":3,"doc-seo-81513-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},81513,1099513958762,"Logic","https://ap-avatar.wpscdn.com/avatar/1000023916a998db790?x-image-process=image/resize,m_fixed,w_180,h_180&k=1784791008015729253",8,"Research & Report","VerteNet: A Multi-Context Hybrid CNN Transformer for Vertebral Landmark Localization in Lateral Spine DXA Images","Vertebral landmarks localization (VLL) in dual energy X-ray absorptiometry (DXA) lateral spine imaging (LSI) is essential for assessing spinal alignment, supporting vertebral fracture assessment (VFA), and enabling intervertebral guide placement for abdominal aortic calcification (AAC) quantification. DXA LSI is cost-effective and low-radiation but remains difficult due to low signal-to-noise ratios and imaging artifacts. VerteNet introduces a dual-resolution attention architecture that integrates local and global context to improve vertebral corner localization. Evaluated on DXA LSIs from multiple machines, it achieves strong accuracy and robustness, outperforming recent state-of-the-art methods.","VerteNet-A Multi-Context Hybrid CNN Transformer for Accurate Vertebral Landmark Localization in Lateral Spine DXA Images  \nArooba Maqsooda,b , Zaid Ilyasa,b , Afsah Saleema,b , Erchuan Zhangc , David Sutera,b , Parminder Rainag , Jonathan M. Hodgsonb,d, John T. Schousboee , William D. Leslief , Joshua R. Lewisa,b and Syed Zulqarnain Gilania,b,h  \na Center for AI & ML, School of Science, Edith Cowan University, Joondalup, Western Australia b Nutrition and Health Innovation Research Institute, Edith Cowan University, Joondalup, Western Australia c School of Science, Sun Yat-sen University, Guangzhou, China  \nd School of Medical and Health Sciences, Edith Cowan University, Joondalup, Western Australia e Park Nicollet Clinic and HealthPartners Institute, Minnesota, USA  \nf Department of Medicine and Radiology, University of Manitoba, Manitoba, Canada g Department of Health Sciences, McMaster University, Hamilton, Canada  \nh Computer Science and Software Engineering, The University of Western Australia, Perth, Western Australia  \narXiv :2502 .02097v4 [ cs .CV] 10 Jul 2026  \nARTICLE INFO  \nKeywords:  \nLateral Spine Imaging  \nAbdominal Aortic Calcification Vertebral Fracture Assessment Dual Energy X-Ray Absorptiometry Medical Imaging  \nAB STRACT  \nVertebral Landmarks Localization (VLL) in Dual Energy X-Ray Absorptiometry (DXA)-based Lateral Spine Imaging (LSI) plays a critical role in evaluating spinal alignment, Vertebral Fracture Assessment (VFA), and facilitating intervertebral guide placement for Abdominal Aortic Calcification (AAC) quantification. While DXA LSI offers advantages such as reduced cost and lower radiation exposure, its analysis remains challenging due to a low signal-to-noise ratio and imaging artifacts. Artificial Intelligence (AI) presents a promising avenue for improving the precision and accuracy of VLL. This study introduces a novel architecture that employs dual-resolution attention mechanisms to capture both fine-grained local details and broader contextual information. Our approach enhances feature integration by leveraging skip connections and decoder layers through dual-resolution selfand cross-attentions. This design improves the model’s ability to learn complex patterns, ensuring precise vertebral corner localization while maintaining both local and global contextual awareness. We evaluated our proposed framework on DXA LSIs acquired from various machines and found that it outperformed recent state-of-the-art architectures, trained for VLL, achieving a normalized mean error of 4.92 and a normalized median error of 2.35 . The proposed framework, VerteNet, enables highly accurate VLLinDXALSI images from diverse machines and demonstrates superior robustness to low signal-to-noise ratios, owing to its enhanced ability to capture both fine-grained local details and broader contextual information.  \n1. Introduction  \nLateral Spine Images (LSIs) are a cornerstone in musculoskeletal diagnostics, providing critical insights for both disease detection and treatment planning. Key applications include spinal alignment assessment to diagnose abnormal curvature conditions such as kyphosis [17] and lordosis [30], Vertebral Fractures Assessment (VFA) [31], Bone Mineral Density (BMD) calculation for osteoporosis analysis [2], Abdominal Aortic Calcification (AAC) detection [24, 25], and visceral fat estimation [19] . These LSIs can be acquired through various imaging modalities, including Computed Tomography (CT), Digital X-Ray Imaging (DXI), Magnetic Resonance Imaging (MRI) or Dual-Energy X-ray Absorptiometry (DXA) (refer to Figure 1 for visual comparison) . Among these, DXA scans are the fastest, most cost-effective, and low-radiation option, making it the preferred modality for vertebral fracture assessment in routine osteoporosis screening. Traditionally, DXA scans are widely used for  \n∗Corresponding Author: Arooba Maqsood  \n [a.maqsood@ecu.edu.au](a.maqsood@ecu.edu.au) (A. Maqsood) ORCID(s):  \nBMD measurement [2] .","cbCaivXNhjQFa6KM","https://ap.wps.com/l/cbCaivXNhjQFa6KM","pdf",6954178,3,1,12,"English","en",105,"# Introduction\n## Lateral Spine Imaging and Clinical Applications\n## AAC Quantification and the Need for Accurate Vertebral Localization","[{\"question\":\"Why is vertebral landmark localization important in DXA lateral spine imaging?\",\"answer\":\"It enables accurate spinal alignment assessment, supports vertebral fracture assessment (VFA), and facilitates intervertebral guide placement needed for abdominal aortic calcification (AAC) quantification.\"},{\"question\":\"What makes VLL on DXA lateral spine images challenging?\",\"answer\":\"DXA LSI analysis is difficult because of low signal-to-noise ratios and imaging artifacts that obscure key anatomical boundaries.\"},{\"question\":\"How does VerteNet improve vertebral landmark localization accuracy?\",\"answer\":\"VerteNet uses a multi-context hybrid CNN-transformer design with dual-resolution attention and skip connections/decoder layers to integrate fine local details with broader contextual information.\"}]",1784173920,30,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"vertenet-a-multi-context-hybrid-cnn-transformer-for-vertebral-landmark-localization-in-lateral-spine-dxa-images","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":20},"https://docshare.wps.com/document/research-report/",{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/vertenet-a-multi-context-hybrid-cnn-transformer-for-vertebral-landmark-localization-in-lateral-spine-dxa-images/81513/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-22","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is vertebral landmark localization important in DXA lateral spine imaging?","Question",{"text":75,"@type":76},"It enables accurate spinal alignment assessment, supports vertebral fracture assessment (VFA), and facilitates intervertebral guide placement needed for abdominal aortic calcification (AAC) quantification.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What makes VLL on DXA lateral spine images challenging?",{"text":80,"@type":76},"DXA LSI analysis is difficult because of low signal-to-noise ratios and imaging artifacts that obscure key anatomical boundaries.",{"name":82,"@type":73,"acceptedAnswer":83},"How does VerteNet improve vertebral landmark localization accuracy?",{"text":84,"@type":76},"VerteNet uses a multi-context hybrid CNN-transformer design with dual-resolution attention and skip connections/decoder layers to integrate fine local details with broader contextual information.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,122,127,130,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":29,"slug":121},"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]